Dockerfile

# Use Python 3.10 slim image for smaller size
FROM python:3.10-slim

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
ENV TRANSFORMERS_CACHE=/app/.cache
ENV HF_HOME=/app/.cache

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    ffmpeg \
    git \
    && rm -rf /var/lib/apt/lists/*

# Create non-root user for security
RUN useradd -m -u 1000 appuser

# Set working directory
WORKDIR /app

# Copy requirements first (for Docker layer caching)
COPY requirements.txt .

# Install Python dependencies
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Create cache directory with proper permissions
RUN mkdir -p /app/.cache && chown -R appuser:appuser /app

# Switch to non-root user
USER appuser

# Expose port (Hugging Face Spaces uses 7860)
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python -c "import requests; requests.get('http://localhost:7860/api/health')" || exit 1

# Run with gunicorn for production
# - timeout 600s for long model loading times
# - workers 1 to save memory (models are heavy)
# - threads 4 for concurrent requests
CMD ["gunicorn", "--bind", "0.0.0.0:7860", "--timeout", "600", "--workers", "1", "--threads", "4", "app:app"]